#!/usr/bin/env python3 """ Enhanced placeholder scanner for HTML template files. - Scans for ###PLACEHOLDER### values - Checks for matched ###IF_xx### and ###END_IF_xx### pairs - Identifies placeholders only in non-English files """ import os import re import argparse from pathlib import Path from collections import defaultdict, Counter import sys # Configuration DIRECTORIES = ['cc', 'ww'] LANGUAGES = ['en', 'es', 'fr', 'de', 'it', 'pt'] # Known valid non-English placeholders (product 200307 is for non-English users) VALID_NON_ENGLISH_PLACEHOLDERS = { 'FIRSTPRICEYR_200307', 'PRICEMONTH_200307', 'PRICEYR_200307' } def extract_placeholders(content): """Extract all ###PLACEHOLDER### values from content.""" pattern = r'###([A-Z_][A-Z0-9_]*)###' matches = re.findall(pattern, content) return sorted(set(matches)) def extract_if_blocks(content): """Extract and validate ###IF_xx### and ###END_IF_xx### pairs.""" # Find all IF and END_IF placeholders if_pattern = r'###(IF_[A-Z0-9_]+)###' end_if_pattern = r'###(END_IF_[A-Z0-9_]+)###' if_matches = [(m.group(1), m.start()) for m in re.finditer(if_pattern, content)] end_if_matches = [(m.group(1), m.start()) for m in re.finditer(end_if_pattern, content)] # Helper function to convert position to line number def pos_to_line(pos): return content[:pos].count('\n') + 1 # Check for matching pairs errors = [] stack = [] # Combine and sort by position all_matches = [] for match, pos in if_matches: all_matches.append(('IF', match, pos)) for match, pos in end_if_matches: all_matches.append(('END_IF', match, pos)) all_matches.sort(key=lambda x: x[2]) # Sort by position for match_type, match_name, pos in all_matches: line_num = pos_to_line(pos) if match_type == 'IF': stack.append((match_name, line_num)) elif match_type == 'END_IF': expected_if = match_name.replace('END_IF_', 'IF_') if not stack: errors.append(f"Unmatched {match_name} at line {line_num}") elif stack[-1][0] != expected_if: errors.append(f"Mismatched {match_name} at line {line_num}, expected END_{stack[-1][0]}") else: stack.pop() # Check for unclosed IF blocks for unclosed, line_num in stack: errors.append(f"Unclosed {unclosed} (opened at line {line_num})") return errors def scan_file(file_path): """Scan a single HTML file for placeholders and IF/END_IF blocks.""" try: with open(file_path, 'r', encoding='utf-8') as f: content = f.read() placeholders = extract_placeholders(content) if_errors = extract_if_blocks(content) return placeholders, if_errors except Exception as e: print(f"Error reading {file_path}: {e}") return [], [f"File read error: {e}"] def scan_directory(dir_path, lang): """Scan all HTML files in a directory.""" results = {} if not os.path.exists(dir_path): return results html_files = Path(dir_path).glob('*.html') for file_path in html_files: relative_path = str(file_path).replace('\\', '/') placeholders, if_errors = scan_file(file_path) results[relative_path] = { 'placeholders': placeholders, 'if_errors': if_errors, 'language': lang } return results def main(): parser = argparse.ArgumentParser(description='Scan HTML template files for placeholders and IF/END_IF blocks') parser.add_argument('--verbose', action='store_true', help='Show all placeholder analysis (not just errors)') parser.add_argument('--file', type=str, help='Scan only a specific file') args = parser.parse_args() if args.file: # Scan single file if not os.path.exists(args.file): print(f"Error: File {args.file} not found") return print(f"Scanning single file: {args.file}\n") placeholders, if_errors = scan_file(args.file) if if_errors: print("IF/END_IF BLOCK ERRORS:") print("-" * 40) for error in if_errors: print(f" ❌ {error}") else: print("✅ All IF/END_IF blocks are properly matched!") if args.verbose: print(f"\nPlaceholders found ({len(placeholders)}):") print("-" * 40) for placeholder in placeholders: print(f" ###{placeholder}###") return print("Scanning HTML template files for placeholders and IF/END_IF blocks...\n") all_placeholders = defaultdict(list) file_results = {} english_placeholders = defaultdict(list) if_errors_found = {} # Scan all directories and languages for directory in DIRECTORIES: for lang in LANGUAGES: scan_dir = os.path.join(directory, lang) if not args.verbose: print(f"Scanning: {scan_dir}") results = scan_directory(scan_dir, lang) file_results.update(results) for file_path, data in results.items(): # Collect placeholders for placeholder in data['placeholders']: all_placeholders[placeholder].append(file_path) # Store English placeholders separately if lang == 'en': filename = os.path.basename(file_path) english_placeholders[filename].extend(data['placeholders']) english_placeholders[filename] = sorted(set(english_placeholders[filename])) # Store IF/END_IF errors if data['if_errors']: if_errors_found[file_path] = data['if_errors'] print(f"\n{'=' * 80}") print("IF/END_IF BLOCK VALIDATION") print(f"{'=' * 80}\n") if if_errors_found: print("ERRORS FOUND:") print("-" * 60) for file_path, errors in if_errors_found.items(): print(f"\n{file_path}:") for error in errors: print(f" ❌ {error}") else: print("✅ All IF/END_IF blocks are properly matched!") if args.verbose: print(f"\n{'=' * 80}") print("SUSPICIOUS PLACEHOLDERS (only in non-English files)") print(f"{'=' * 80}\n") # Find placeholders that only appear in non-English files non_english_only = {} for placeholder, files in all_placeholders.items(): appears_in_english = any('/en/' in file for file in files) non_english_files = [file for file in files if '/en/' not in file] if not appears_in_english and non_english_files: # Skip known valid non-English placeholders if placeholder not in VALID_NON_ENGLISH_PLACEHOLDERS: non_english_only[placeholder] = non_english_files if args.verbose: if not non_english_only: print("✅ No suspicious placeholders found!") else: for placeholder in sorted(non_english_only.keys()): print(f"###{placeholder}###") print(" Found in:") for file in non_english_only[placeholder]: print(f" - {file}") print() elif non_english_only: print("ERRORS: Suspicious placeholders found (use --verbose to see details)") for placeholder in sorted(non_english_only.keys()): print(f" ❌ ###{placeholder}### (only in non-English files)") if args.verbose: print(f"\n{'=' * 80}") print("PLACEHOLDER FREQUENCY ANALYSIS") print(f"{'=' * 80}\n") # Sort placeholders by frequency placeholder_counts = {p: len(files) for p, files in all_placeholders.items()} sorted_placeholders = sorted(placeholder_counts.items(), key=lambda x: x[1], reverse=True) print("Most common placeholders:") print("-" * 40) for i, (placeholder, count) in enumerate(sorted_placeholders[:20]): print(f"###{placeholder}###".ljust(32) + f"{count} files") print(f"\n{'=' * 80}") print("ENGLISH TEMPLATE REFERENCE") print(f"{'=' * 80}\n") print("Placeholders used in English templates:") print("-" * 50) for filename in sorted(english_placeholders.keys()): placeholders = english_placeholders[filename] if placeholders: print(f"\n{filename}:") for placeholder in placeholders: print(f" ###{placeholder}###") if __name__ == "__main__": main()